Single-cell and spatial-omics technologies provide insights into cancer samples at unprecedented resolution, but currently only assay a narrow range of modalities. This misses opportunities and information available from profiling the genome and other omics. Additionally, many well-annotated clinical samples are already assayed using bulk technologies. To address these gaps, this project will develop machine learning and statistical approaches to integrate omics signals across resolutions and modalities. The outcome will be an improved view of the biological processes and tumour states present in bulk data from well-annotated clinical samples, as well as extending insights from small high quality single-cell cohorts to large public bulk cohorts. The lab has several remarkable datasets that will provide exciting opportunities to apply these methods.
This project is eligible for the WEHI Artificial Intelligence (AI) & Machine Learning (ML) PhD Scholarship and is open to both domestic and international students.
